6
$\begingroup$

One of the breakthroughs of econometrics over the past two decades has been to employ "clustering" to take into account the correlation of error terms across observations. For instance, if you're evaluating the effect of an educational intervention where you have data on individual students but you suspect that teachers implemented the intervention differently, it is common to analyze the data in a way that recognizes that there are common effects at the "class" level. A common correction is to use clustering.

When you run a regression discontinuity, do you similarly have to take into account that your observations may be clustered? If so, how is the estimator implemented differently?

$\endgroup$
  • 1
    $\begingroup$ Could you give some references? It is a first time I hear about this breakthrough. Also what do you mean by regression discontinuity? $\endgroup$ – mpiktas Oct 16 '11 at 10:19
  • 2
    $\begingroup$ Clustering first gained notoriety with the so-called "Moulton critique" discussed here: sciencedirect.com/science/article/pii/0304407686900217. A more recent example of the danger of not-clustering was presented in: nber.org/papers/w8841. You can read about RD here: en.wikipedia.org/wiki/Regression_discontinuity_design $\endgroup$ – d_a_c321 Oct 16 '11 at 14:48
  • 1
    $\begingroup$ @lejohn, yes I think too, but this is exactly the term OP used. If I understand correctly it is simply robust standard errors for panel data type models. $\endgroup$ – mpiktas Nov 14 '11 at 9:14
  • 1
    $\begingroup$ -1 This question does not provide enough information to allow for a constructive answer. $\endgroup$ – baha-kev Feb 27 '12 at 1:38
1
$\begingroup$

Whether you take into account clustering or not only affects the standard errors of your estimates. In a situation like yours, I would not focus too much on the standard errors. It is much more important that you can justify the use of the regression discontinuity framework, and you have to be able to show that it allows recovering the parameter(s) you are interested in. Once you are sure about this you can go a step further.

This next step would be the following. If you are concerned about these class effects, you should have a look at multilevel regression models. It should be possible to implement a regression discontinuity strategy within a multilevel model.

$\endgroup$
  • $\begingroup$ rescued from a deleted answer $\endgroup$ – EnergyNumbers Dec 24 '11 at 10:38
  • $\begingroup$ Agreed; if you are worried about the efficiency of your coefficient estimates, using "clustered standard errors" might be fruitful. But as mentioned, this is a separate (and minor!) issue compared with your regression discontinuity experimental design. $\endgroup$ – baha-kev Feb 27 '12 at 1:38
0
$\begingroup$

Is it a regular linear regression model or not? In Quantitative finance we have the same problem. we use a GARCH model to estimate volatility, however volatility does not seem to be normally distributed and seems to cluster. for this we use a switching garch model. this "switching" model differentiates and switches between different clustering regions. you could look into this switching it might be usefull...

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.